© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 97499
    Prev
    Next
    INDEX
    Explanations

    file

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MainAxisSize
    -0.82
     CreateTagHelper
    -0.74
    Hochspringen
    -0.73
    MethodManager
    -0.62
    ftances
    -0.60
    Tikang
    -0.59
    stalt
    -0.58
    UniformLocation
    -0.57
     дописавши
    -0.56
     trương
    -0.56
    POSITIVE LOGITS
    rrggbb
    0.56
    InstanceState
    0.51
     HED
    0.49
    pidou
    0.47
    󠁿
    0.46
    THISDAY
    0.45
    إنه
    0.44
    <bos>
    0.41
     Warzone
    0.41
    ]-->
    0.40
    Activations Density 0.140%

    No Known Activations